diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index a9d2aee3826f470d6966fcbcad1ef8fa822782cf..1e25cd80589e7370eee54dedb18d355d3bf66e48 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -225,12 +225,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	}
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	unsigned long addr)
 {
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index e7da41aa91100be88bf8a723f410e1d3ef8d8b31..77e541cf0e5d560b4325511f2c18d050d2ca5ddf 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -242,12 +242,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	}
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 /*
  * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
  * PTE, not just those pointing to (normal) physical memory.
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 30759b5608497407a699877304d356edc8d9c014..15711de1040358098fd864caad1d1f3b472b2301 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -98,11 +98,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	free_page_and_swap_cache(page);
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
+
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 /*
  * pte_free_tlb frees a pte table and clears the CRSTE for the
  * page table from the tlb.
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 21ae8f5546b20a0bde08d5892d2d6d1fca7bf994..025cdb1032f6f9db7f30cfa54ccf10047772ee83 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -109,12 +109,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 #define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
 #define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
 #define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 3dc4cbb3c2c0a6e872d1b371eb8f9e1f0835deee..821ff0acfe17f7f9e4264be04d7d346731bd6b4e 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -110,12 +110,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	__tlb_remove_page(tlb, page);
 }
 
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size)
+{
+	return __tlb_remove_page(tlb, page);
+}
+
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb,
 					 struct page *page)
 {
 	return __tlb_remove_page(tlb, page);
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	return tlb_remove_page(tlb, page);
+}
+
 /**
  * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
  *
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 7b899a46a4cb8efa13e2dad9d22820b3b1389ed5..c6d6671876080e9bdc48b820bb5b5d8d362a470b 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -112,6 +112,7 @@ struct mmu_gather {
 	 * that that we can adjust the range after the flush
 	 */
 	unsigned long addr;
+	int page_size;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
@@ -120,7 +121,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
 							unsigned long end);
-bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address)
@@ -145,23 +147,36 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+static inline void tlb_remove_page_size(struct mmu_gather *tlb,
+					struct page *page, int page_size)
+{
+	if (__tlb_remove_page_size(tlb, page, page_size)) {
+		tlb_flush_mmu(tlb);
+		tlb->page_size = page_size;
+		__tlb_adjust_range(tlb, tlb->addr);
+		__tlb_remove_page_size(tlb, page, page_size);
+	}
+}
+
+static bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	return __tlb_remove_page_size(tlb, page, PAGE_SIZE);
+}
+
 /* tlb_remove_page
  *	Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when
  *	required.
  */
 static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 {
-	if (__tlb_remove_page(tlb, page)) {
-		tlb_flush_mmu(tlb);
-		__tlb_adjust_range(tlb, tlb->addr);
-		__tlb_remove_page(tlb, page);
-	}
+	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
 static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page)
 {
 	/* active->nr should be zero when we call this */
 	VM_BUG_ON_PAGE(tlb->active->nr, page);
+	tlb->page_size = PAGE_SIZE;
 	__tlb_adjust_range(tlb, tlb->addr);
 	return __tlb_remove_page(tlb, page);
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 343a2b7e57aa25f7d02709ff13ab8a5e47c68a87..23d1bf42fef105e85e8e452d663cd6c2d5d6fdac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1689,7 +1689,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd));
 		atomic_long_dec(&tlb->mm->nr_ptes);
 		spin_unlock(ptl);
-		tlb_remove_page(tlb, page);
+		tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE);
 	}
 	return 1;
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 524c078ce67b2708c10de1504d279159420256d6..a9a8c313d133b97273ef073e72dcb7e3edf19690 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3250,7 +3250,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		page_remove_rmap(page, true);
 
 		spin_unlock(ptl);
-		tlb_remove_page(tlb, page);
+		tlb_remove_page_size(tlb, page, huge_page_size(h));
 		/*
 		 * Bail out after unmapping reference page if supplied
 		 */
diff --git a/mm/memory.c b/mm/memory.c
index 12f31501c3231813086c64102911b4f7404bdbb0..a329149e1c5448087a8d4fd1b42f1c23ad393bd1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -233,6 +233,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
 #endif
+	tlb->page_size = 0;
 
 	__tlb_reset_range(tlb);
 }
@@ -294,12 +295,19 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
  *	When out of page slots we must call tlb_flush_mmu().
  *returns true if the caller should flush.
  */
-bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
 
+	if (!tlb->page_size)
+		tlb->page_size = page_size;
+	else {
+		if (page_size != tlb->page_size)
+			return true;
+	}
+
 	batch = tlb->active;
 	if (batch->nr == batch->max) {
 		if (!tlb_next_batch(tlb))